Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 911 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.1115. Min Range: -5.1115

Max Act: 5.1115. Min Act: -0.1700

Data Index: 1472522 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 5.1115. Min Range: -5.1115

Max Act: 5.0029. Min Act: -0.1700

Data Index: 1435128 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.9836. Min Act: -0.1700

Data Index: 731327 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.9474. Min Act: -0.1700

Data Index: 363273 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.9648. Min Act: -0.1700

Data Index: 1447702 (Python Code)

Max Activating Token Index: 782

Text #5

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.9212. Min Act: -0.1700

Data Index: 761250 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.9504. Min Act: -0.1700

Data Index: 654244 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8976. Min Act: -0.1700

Data Index: 338775 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.9053. Min Act: -0.1700

Data Index: 330896 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8639. Min Act: -0.1700

Data Index: 320947 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8766. Min Act: -0.1700

Data Index: 1542944 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8656. Min Act: -0.1700

Data Index: 1593869 (Python Code)

Max Activating Token Index: 350

Text #12

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8257. Min Act: -0.1700

Data Index: 1638276 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8300. Min Act: -0.1700

Data Index: 765269 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8398. Min Act: -0.1700

Data Index: 1217337 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8351. Min Act: -0.1700

Data Index: 354482 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8116. Min Act: -0.1700

Data Index: 800914 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8209. Min Act: -0.1700

Data Index: 1215765 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8161. Min Act: -0.1700

Data Index: 1446613 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 5.1115. Min Range: -5.1115

Max Act: 4.8029. Min Act: -0.1700

Data Index: 1394163 (Python Code)

Max Activating Token Index: 149